The main goal of this article is to propose estimators for the Spatial Lag Model (SLM) under miss-ing data context. We present three alternatives estimators for the SLM based on Two Stage LeastSquares estimation methodology. The estimators are efficient within their type and consistentunder random missing data in the dependent variable. Unlike the IBG2SLS estimator presentedin Wang and Lee (2013) which impute all missing data we only impute missing data in the spatiallag. Our first proposal is an alternative version of the IBG2SLS estimator, the second one is basedon an approximation to the optimal instruments matrix and the third one is an alternative√n-equivalent to the first. Thorough a Monte Carlo simulation we assess the estimators performanceunder finite samples. Results show a good performance for all estimators, moreover, results arequite similar to the IBG2SLS estimator suggesting that a complete imputation (as IBG2SLS does)does not add information.
© 2001-2024 Fundación Dialnet · Todos los derechos reservados